Chiu-Han Hsiao

Mr. Chiu-Han Hsiao


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 May 2022 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Open access
CHChiu-Han Hsiao
Chiu-Han Hsiao
PLPing-Cherng Lin
Ping-Cherng Lin
LCLi-An Chung
Li-An Chung
FLFrank Yeong-Sung Lin
Frank Yeong-Sung Lin
FYFeng-Jung Yang
Feng-Jung Yang
TSTzu-Lung Sun
Tzu-Lung Sun
This paper proposes an encoder-decoder architecture for kidney segmentation. A hyperparameter optimization process is implemented, including the development of a model architecture, selecting a windowing method and a loss function, and data augmentation. The model consists of EfficientNet-B5 as the encoder and a feature pyramid network as the decoder that yields the best performance with a Dice score of 0.969 on the 2019 Kidney and Kidney Tumor Segmentation Challenge dataset. The proposed model is tested with different voxel spacing, anatomical planes, and kidney and tumor volumes. Moreover, case studies are conducted to analyze segmentation outliers. Finally, five-fold cross-validation and the 3D-IRCAD-01 dataset are used to evaluate the developed model in terms of the following evaluation metrics: the Dice score, recall, precision, and the Intersection over Union score. A new development and application of artificial intelligence algorithms to solve image analysis and interpretation will be demonstrated in this paper. Overall, our experiment results show that the proposed kidney segmentation solutions in CT images can be significantly applied to clinical needs to assist surgeons in surgical planning. It enables the calculation of the total kidney volume for kidney function estimation in ADPKD and supports radiologists or doctors in disease diagnoses and disease progression.

9 May 2022 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Open access
CHChiu-Han Hsiao
Chiu-Han Hsiao
TSTzu-Lung Sun
Tzu-Lung Sun
PLPing-Cherng Lin
Ping-Cherng Lin
TPTsung-Yu Peng
Tsung-Yu Peng
YCYu-Hsin Chen
Yu-Hsin Chen
YHYennun Huang
Yennun Huang
Previously, doctors interpreted computed tomography (CT) images based on their experience in diagnosing kidney diseases. However, with the rapid increase in CT images, such interpretations were required considerable time and effort, producing inconsistent results. Several novel neural network models were proposed to automatically identify kidney or tumor areas in CT images for solving this problem. In most of these models, only the neural network structure was modified to improve accuracy. However, data pre-processing was also a crucial step in improving the results. This study systematically discussed the necessary pre-processing methods before processing medical images in a neural network model. The experimental results were shown that the proposed pre-processing methods or models significantly improve the accuracy rate compared with the case without data pre-processing. Specifically, the dice score was improved from 0.9436 to 0.9648 for kidney segmentation and 0.7294 for all types of tumor detections. The performance was suitable for clinical applications with lower computational resources based on the proposed medical image processing methods and deep learning models. The cost efficiency and effectiveness were also achieved for automatic kidney volume calculation and tumor detection accurately.

29 May 2023 in IEEE Access
Verified
Journal Article
Open access
KTKuang-Yen TAI
Kuang-Yen TAI
FLFrank Yeong-Sung Lin
Frank Yeong-Sung Lin
CHChiu-Han Hsiao
Chiu-Han Hsiao
At a significant moment in the rapid development of cloud technology, large-scale cloud computing centers have emerged. With the emergence of the internet and artificial intelligence, enormous computing resources are required to process data and train machine learning models. The architecture of cloud computing centers involves millions of computing resources, and improper management of these resources can increase operating costs and exert tremendous pressure on the environment. This study proposes an optimized computing resource and energy management algorithm for computing centers with heterogeneous computing resources from the perspective of Green IT. Specifically, this study models the energy consumption at each point in time and the relationship between tasks and also considers the calculation of data backup. This approach will be expanded to optimize decisions for all computing tasks in computing centers based on the sequence of tasks and energy consumption while considering heterogeneous computing resources, energy efficiency, task scheduling, and execution time. By modeling this issue as a highly nonlinear optimization problem and utilizing mathematical programming and Lagrangian relaxation, we propose an optimized energy management algorithm to effectively manage computing resources and create cloud computing centers with high performance and low energy consumption.

11 June 2022 in International Journal of Gastronomy and Food Science
Verified
Journal Article
Closed access
YCYevvon Yi-Chi Chang
Yevvon Yi-Chi Chang
JLJo-Hui Lin
Jo-Hui Lin
CHChiu-Han Hsiao
Chiu-Han Hsiao

13 May 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Open access
CHChiu-Han Hsiao
Chiu-Han Hsiao
FLFrank Yeong-Sung Lin
Frank Yeong-Sung Lin
TSTzu-Lung Sun
Tzu-Lung Sun
YLYen-Yen Liao
Yen-Yen Liao
CWChih-Horng Wu
Chih-Horng Wu
YHYennun Huang
Yennun Huang
Hepatocellular carcinoma (HCC), the most common type of liver cancer, poses significant challenges in detection and diagnosis. Medical imaging, especially computed tomography (CT), is pivotal in non-invasively identifying this disease, requiring substantial expertise for interpretation. This research introduces an innovative strategy that integrates two-dimensional (2D) and three-dimensional (3D) deep learning models within a federated learning (FL) framework for precise segmentation of liver and tumor regions in medical images. The study utilized 131 CT scans from the Liver Tumor Segmentation (LiTS) challenge and demonstrated the superior efficiency and accuracy of the proposed Hybrid-ResUNet model with a Dice score of 0.9433 and an AUC of 0.9965 compared to ResNet and EfficientNet models. This FL approach is beneficial for conducting large-scale clinical trials while safeguarding patient privacy across healthcare settings. It facilitates active engagement in problem-solving, data collection, model development, and refinement. The study also addresses data imbalances in the FL context, showing resilience and highlighting local models' robust performance. Future research will concentrate on refining federated learning algorithms and their incorporation into the continuous implementation and deployment (CI/CD) processes in AI system operations, emphasizing the dynamic involvement of clients. We recommend a collaborative human-AI endeavor to enhance feature extraction and knowledge transfer. These improvements are intended to boost equitable and efficient data collaboration across various sectors in practical scenarios, offering a crucial guide for forthcoming research in medical AI.

9 January 2023 in Sensors
Verified
Journal Article
Open access
PDF file
KTKuang-Yen TAI
Kuang-Yen TAI
BLBO-CHEN LIU
BO-CHEN LIU
CHChiu-Han Hsiao
Chiu-Han Hsiao
MTMING-CHI TSAI
MING-CHI TSAI
FLFrank Yeong-Sung Lin
Frank Yeong-Sung Lin
The rapid development of AIOT-related technologies has revolutionized various industries. The advantage of such real-time sensing, low costs, small sizes, and easy deployment makes extensive use of wireless sensor networks in various fields. However, due to the wireless transmission of data, and limited built-in power supply, controlling energy consumption and making the application of the sensor network more efficient is still an urgent problem to be solved in practice. In this study, we construct this problem as a tree structure wireless sensor network mathematical model, which mainly considers the QoS and fairness requirements. This study determines the probability of sensor activity, transmission distance, and transmission of the packet size, and thereby minimizes energy consumption. The Lagrangian Relaxation method is used to find the optimal solution with the lowest energy consumption while maintaining the network’s transmission efficiency. The experimental results confirm that the decision-making speed and energy consumption can be effectively improved.